A Rationale-centric Counterfactual Data Augmentation Method for Cross-Document Event Coreference Resolution
This addresses the issue of bias in cross-document event coreference resolution for NLP applications, representing an incremental improvement over existing methods.
The paper tackled the problem of event coreference resolution systems relying on spurious lexical matching patterns by developing a rationale-centric counterfactual data augmentation method using LLMs, achieving state-of-the-art performance on three benchmarks and showing robustness in out-of-domain scenarios.
Based on Pre-trained Language Models (PLMs), event coreference resolution (ECR) systems have demonstrated outstanding performance in clustering coreferential events across documents. However, the existing system exhibits an excessive reliance on the `triggers lexical matching' spurious pattern in the input mention pair text. We formalize the decision-making process of the baseline ECR system using a Structural Causal Model (SCM), aiming to identify spurious and causal associations (i.e., rationales) within the ECR task. Leveraging the debiasing capability of counterfactual data augmentation, we develop a rationale-centric counterfactual data augmentation method with LLM-in-the-loop. This method is specialized for pairwise input in the ECR system, where we conduct direct interventions on triggers and context to mitigate the spurious association while emphasizing the causation. Our approach achieves state-of-the-art performance on three popular cross-document ECR benchmarks and demonstrates robustness in out-of-domain scenarios.